REVIEW 9 cited by
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
read the original abstract
Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional quantization methods face significant memory overhead due to the need to store quantization constants (at least a zero point and a scale) in full precision per data block. Depending on the block size, this overhead can add 1 or 2 bits per quantized number. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss (JL) transform followed by sign-bit quantization. In contrast to existing methods, QJL eliminates memory overheads by removing the need for storing quantization constants. We propose an asymmetric estimator for the inner product of two vectors and demonstrate that applying QJL to one vector and a standard JL transform without quantization to the other provides an unbiased estimator with minimal distortion. We have developed an efficient implementation of the QJL sketch and its corresponding inner product estimator, incorporating a lightweight CUDA kernel for optimized computation. When applied across various LLMs and NLP tasks to quantize the KV cache to only 3 bits, QJL demonstrates a more than fivefold reduction in KV cache memory usage without compromising accuracy, all while achieving faster runtime. Codes are available at \url{https://github.com/amirzandieh/QJL}.
Forward citations
Cited by 9 Pith papers
-
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
-
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
HyperQuant unifies Hadamard transform, optimal lattice quantization, and entropy coding to outperform prior schemes on LLM weight and KV cache quantization down to 1.7 bits per scalar while preserving quality on a 19B...
-
Runtime-Certified Bounded-Error Quantized Attention
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.
-
Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant
At 4-bit budget KQV wins on KL divergence, geometric K error and 6D distance with unconditional K-V asymmetry; QKQV wins geometrically at other budgets because the Jensen-amplified variance inflation from QJL on K doe...
-
Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
-
AXELRAM: Quantize Once, Never Dequantize
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
-
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a fac...
-
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
UltraQuant applies 4-bit KV caching with TurboQuant-style rotation and custom AMD kernels to context-heavy agent workloads, delivering 3.47x P50 TTFT reduction in cache-pressured rounds and 1.63x throughput gain over FP8.
-
Hierarchical vs. Flat Iteration in Shared-Weight Transformers
Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.